Whisper Small Uz - Aslon Khamidov -- with Uzbek Voice dataset
This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3910
- Wer: 35.9465
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4411 | 0.0176 | 1000 | 0.5526 | 47.9128 |
| 0.327 | 0.0352 | 2000 | 0.4648 | 41.1885 |
| 0.2883 | 0.0528 | 3000 | 0.4286 | 37.6822 |
| 0.2777 | 0.0704 | 4000 | 0.4037 | 36.9479 |
| 0.2543 | 0.0880 | 5000 | 0.3910 | 35.9465 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.0
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 18